gregorgabrovsek commited on
Commit
d02da6e
1 Parent(s): 96d1731

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "0",
14
+ "1": "1",
15
+ "2": "2",
16
+ "3": "3",
17
+ "4": "4",
18
+ "5": "5",
19
+ "6": "6",
20
+ "7": "7",
21
+ "8": "8",
22
+ "9": "9",
23
+ "10": "10",
24
+ "11": "11",
25
+ "12": "12",
26
+ "13": "13",
27
+ "14": "14",
28
+ "15": "15",
29
+ "16": "16",
30
+ "17": "17",
31
+ "18": "18",
32
+ "19": "19",
33
+ "20": "20",
34
+ "21": "21",
35
+ "22": "22",
36
+ "23": "23",
37
+ "24": "24",
38
+ "25": "25",
39
+ "26": "26",
40
+ "27": "27",
41
+ "28": "28",
42
+ "29": "29",
43
+ "30": "30",
44
+ "31": "31",
45
+ "32": "32",
46
+ "33": "33",
47
+ "34": "34",
48
+ "35": "35",
49
+ "36": "36",
50
+ "37": "37",
51
+ "38": "38",
52
+ "39": "39",
53
+ "40": "40",
54
+ "41": "41",
55
+ "42": "42",
56
+ "43": "43",
57
+ "44": "44",
58
+ "45": "45",
59
+ "46": "46",
60
+ "47": "47",
61
+ "48": "48",
62
+ "49": "49",
63
+ "50": "50",
64
+ "51": "51",
65
+ "52": "52",
66
+ "53": "53",
67
+ "54": "54",
68
+ "55": "55",
69
+ "56": "56",
70
+ "57": "57",
71
+ "58": "58",
72
+ "59": "59",
73
+ "60": "60",
74
+ "61": "61",
75
+ "62": "62",
76
+ "63": "63",
77
+ "64": "64",
78
+ "65": "65",
79
+ "66": "66",
80
+ "67": "67",
81
+ "68": "68",
82
+ "69": "69",
83
+ "70": "70",
84
+ "71": "71",
85
+ "72": "72",
86
+ "73": "73",
87
+ "74": "74",
88
+ "75": "75",
89
+ "76": "76",
90
+ "77": "77",
91
+ "78": "78",
92
+ "79": "79",
93
+ "80": "80",
94
+ "81": "81",
95
+ "82": "82",
96
+ "83": "83",
97
+ "84": "84",
98
+ "85": "85",
99
+ "86": "86",
100
+ "87": "87",
101
+ "88": "88",
102
+ "89": "89",
103
+ "90": "90",
104
+ "91": "91",
105
+ "92": "92",
106
+ "93": "93",
107
+ "94": "94",
108
+ "95": "95",
109
+ "96": "96",
110
+ "97": "97",
111
+ "98": "98",
112
+ "99": "99",
113
+ "100": "OOC"
114
+ },
115
+ "initializer_range": 0.02,
116
+ "intermediate_size": 3072,
117
+ "label2id": {
118
+ "0": 0,
119
+ "1": 1,
120
+ "10": 10,
121
+ "11": 11,
122
+ "12": 12,
123
+ "13": 13,
124
+ "14": 14,
125
+ "15": 15,
126
+ "16": 16,
127
+ "17": 17,
128
+ "18": 18,
129
+ "19": 19,
130
+ "2": 2,
131
+ "20": 20,
132
+ "21": 21,
133
+ "22": 22,
134
+ "23": 23,
135
+ "24": 24,
136
+ "25": 25,
137
+ "26": 26,
138
+ "27": 27,
139
+ "28": 28,
140
+ "29": 29,
141
+ "3": 3,
142
+ "30": 30,
143
+ "31": 31,
144
+ "32": 32,
145
+ "33": 33,
146
+ "34": 34,
147
+ "35": 35,
148
+ "36": 36,
149
+ "37": 37,
150
+ "38": 38,
151
+ "39": 39,
152
+ "4": 4,
153
+ "40": 40,
154
+ "41": 41,
155
+ "42": 42,
156
+ "43": 43,
157
+ "44": 44,
158
+ "45": 45,
159
+ "46": 46,
160
+ "47": 47,
161
+ "48": 48,
162
+ "49": 49,
163
+ "5": 5,
164
+ "50": 50,
165
+ "51": 51,
166
+ "52": 52,
167
+ "53": 53,
168
+ "54": 54,
169
+ "55": 55,
170
+ "56": 56,
171
+ "57": 57,
172
+ "58": 58,
173
+ "59": 59,
174
+ "6": 6,
175
+ "60": 60,
176
+ "61": 61,
177
+ "62": 62,
178
+ "63": 63,
179
+ "64": 64,
180
+ "65": 65,
181
+ "66": 66,
182
+ "67": 67,
183
+ "68": 68,
184
+ "69": 69,
185
+ "7": 7,
186
+ "70": 70,
187
+ "71": 71,
188
+ "72": 72,
189
+ "73": 73,
190
+ "74": 74,
191
+ "75": 75,
192
+ "76": 76,
193
+ "77": 77,
194
+ "78": 78,
195
+ "79": 79,
196
+ "8": 8,
197
+ "80": 80,
198
+ "81": 81,
199
+ "82": 82,
200
+ "83": 83,
201
+ "84": 84,
202
+ "85": 85,
203
+ "86": 86,
204
+ "87": 87,
205
+ "88": 88,
206
+ "89": 89,
207
+ "9": 9,
208
+ "90": 90,
209
+ "91": 91,
210
+ "92": 92,
211
+ "93": 93,
212
+ "94": 94,
213
+ "95": 95,
214
+ "96": 96,
215
+ "97": 97,
216
+ "98": 98,
217
+ "99": 99,
218
+ "OOC": 100
219
+ },
220
+ "layer_norm_eps": 1e-12,
221
+ "max_position_embeddings": 512,
222
+ "model_type": "bert",
223
+ "num_attention_heads": 12,
224
+ "num_hidden_layers": 12,
225
+ "pad_token_id": 0,
226
+ "pooler_fc_size": 768,
227
+ "pooler_num_attention_heads": 12,
228
+ "pooler_num_fc_layers": 3,
229
+ "pooler_size_per_head": 128,
230
+ "pooler_type": "first_token_transform",
231
+ "position_embedding_type": "absolute",
232
+ "problem_type": "single_label_classification",
233
+ "torch_dtype": "float32",
234
+ "transformers_version": "4.26.1",
235
+ "type_vocab_size": 2,
236
+ "use_cache": true,
237
+ "vocab_size": 105879
238
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3795d48f25d125fd864906d844a615fbf5d0aee26186db832931411517d788c6
3
+ size 669810585
runs/Aug14_14-14-25_wn201.arnes.si/1692015278.199609/events.out.tfevents.1692015278.wn201.arnes.si.552013.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aebc86acd402bffbca1ded1215f6bb0154dd796a7037e01d4b8593d50ed12a6
3
+ size 5873
runs/Aug14_14-14-25_wn201.arnes.si/events.out.tfevents.1692015277.wn201.arnes.si.552013.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70eeb6994be405e70dd6bcaab3bfbbc7541578bf52071df64968b8a0d073dc81
3
+ size 21997
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-multilingual-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d867d88b7c80ed43cb33fe06d6bde966470e4b5626df3c138f376ef756c2d6a1
3
+ size 3567
vocab.txt ADDED
The diff for this file is too large to render. See raw diff